- virtualenv --python=python3.5 py35
- source py35/bin/activate
- cd [dir of tf-yolo3]
- pip install -r requirements.txt
- Download the DETRAC dataset from detrac_website
- chage the config.py file to the location of your downloaded dataset.
- run script in data to parse XML file.
cd datasets
python XML_parser.py
python image_migrate.py
- If you want to use original pretrained weights for YOLOv3, download from darknet53 weights
- rename it as darknet53.weights, and modify the darknet53_weights_path in the config.py
wget https://pjreddie.com/media/files/darknet53.conv.74`
- Modify the data augmentation parameters and train parameters
- Run yolo_train.py
- Modify the pre_train_yolo3 and model_dir in config.py
- Run detect.py
python detect.py --image_file ./test.jpg
If you want to modify the Gpu index, please modify gpu_index in config.py
@article{yolov3,
title={YOLOv3: An Incremental Improvement},
author={Redmon, Joseph and Farhadi, Ali},
journal = {arXiv},
year={2018}
}